A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia

Ähnliche Einträge

• Filipino Benchmarks for Measuring Sexist and Homophobic Bias in Multilingual Language Models from Southeast Asia
  von: Gamboa, Lance Calvin Lim, et al.
  Veröffentlicht: (2024)
• Bias Attribution in Filipino Language Models: Extending a Bias Interpretability Metric for Application on Agglutinative Languages
  von: Gamboa, Lance Calvin Lim, et al.
  Veröffentlicht: (2025)
• Social Bias in Multilingual Language Models: A Survey
  von: Gamboa, Lance Calvin Lim, et al.
  Veröffentlicht: (2025)
• Robust Bias Evaluation with FilBBQ: A Filipino Bias Benchmark for Question-Answering Language Models
  von: Gamboa, Lance Calvin Lim, et al.
  Veröffentlicht: (2026)
• SeaLLMs -- Large Language Models for Southeast Asia
  von: Nguyen, Xuan-Phi, et al.
  Veröffentlicht: (2023)